主 题: Sparse Additive Index Model for High-Dimensional Data with Grouped Covariates
报告人: Sijian Wang (University of Wisconsin-Madison)
时 间: 2017-06-13 16:00-17:00
地 点: 理科一号楼1418
Abstract: In this talk, motivated by genomic studies, we propose a sparse additive-index model to integrate group information of covariates in the model. The method simultaneously constructs an index for each group and estimates the corresponding link function to connect the index to the response. A novel constraint is proposed to solve the identifiability issue when regularization on index parameters is present. Our proposed method can not only identify important groups, but also select important individual covariates within selected pathways. Furthermore, the proposed method has three good properties: 1) It is flexible to model the nonlinear association between covariates and response; 2) It automatically considers the interactions among covariates within the same group; 3) It may distinguish the effects of a covariate in all of groups it belongs to. We have studied the theoretical properties of the methods. The methods are demonstrated using simulation studies and analysis on a TCGA ovarian cancer dataset.
About the speaker: Dr. Sijian Wang is Associate Professor in the Department of Biostatistics and Medical Informatics and Department of Statistics at the University of Wisconsin-Madison. He obtained his Ph.D. in Biostatistics from the University of Michigan in 2008. His research interests include high-dimensional data analysis, statistical and machine learning, bioinformatics and statistical genomics, precision medicine, and survival analysis and longitudinal data analysis. He has won several paper awards by ENAR, ASA Computing Section, and ICSA, and has published over 40 papers in leading methodological and applied journals such as the Annals of Statistics, Annals of Applied Statistics, Biometrika, Biometrics, and PNAS.
